Visualization for University Brand Image Clustering by Simple Topic Model

Abstract

Bayesian inference is widely used in various application fields such as topic extraction. In the paper, we present our developed simple topic model visualization tool and as its example, we show university brand image clustering. When high school students select a university, their university choice greatly depends on their universities' brand images. Then the university public relations section needs the survey of the brand images. The clustering results is so helpful for the public relations section to make the publicity strategy. We conducted the university clustering with our developed visualization tool. The paper shows that the visualization has great potential to identify whether the Markov chain reaches the equilibrium states and evaluate the burn-in period.